{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/coloring-with-limited-data-few-shot-1","title":"Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks","arxiv_id":"1906.11888","date":"2019-06-09","proceeding":null,"authors":["Seungjoo Yoo","Hyojin Bahng","Sunghyo Chung","Junsoo Lee","Jaehyuk Chang","Jaegul Choo"],"abstract":"Despite recent advancements in deep learning-based automatic colorization, they are still limited when it comes to few-shot learning. Existing models require a significant amount of training data. To tackle this issue, we present a novel memory-augmented colorization model MemoPainter that can produce high-quality colorization with limited data. In particular, our model is able to capture rare instances and successfully colorize them. We also propose a novel threshold triplet loss that enables unsupervised training of memory networks without the need of class labels. Experiments show that our model has superior quality in both few-shot and one-shot colorization tasks.","url_abs":"https://arxiv.org/abs/1906.11888v1","url_pdf":"https://arxiv.org/pdf/1906.11888v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"coloring-with-limited-data-few-shot-1","repo_url":"https://github.com/dongheehand/MemoPainter-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"colorization","method_name":"Colorization"},{"method_slug":"triplet-loss","method_name":"Triplet Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1906.11888","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}